Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description's 'Read-only - does not send messages' partially repeats this. However, the explicit statement about not sending messages adds a specific behavioral guarantee not fully captured by the read-only hint alone. The description does not contradict annotations, and it provides a small additional detail about side-effect-free operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two short sentences that state the purpose and the read-only nature. There is no redundancy or filler, and the key information is front-loaded. Every word earns its place, making it an exemplar of minimal but informative writing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple single-parameter interface, the presence of an output schema, and annotations covering safety, the description covers the essential facts. It does not explain how results are ordered or paginated, but those may be documented in the output schema. The only notable gap is the lack of differentiation from similar tools, which is more of a usage-guideline issue and already penalized there. Overall, the description is sufficient for a straightforward read-only operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for the single 'days' parameter, including a clear range and default. The tool description adds no additional semantics about the parameter, so it relies entirely on the schema. This meets the baseline for high schema coverage, though it does not enhance the parameter understanding beyond what is already available.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states that the tool identifies recent abandoned checkouts with recoverable value, making the core purpose clear. However, it lacks an explicit verb like 'list' or 'retrieve', and it does not distinguish itself from the closely named sibling 'run_win_back_candidates', which could cause confusion. The title 'Abandoned Cart Candidates' reinforces the intent but does not fully differentiate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as 'run_win_back_candidates' or 'run_repeat_purchase_rate'. The description only states what it does, not when it should be selected over other similar tools. No exclusions or preferred contexts are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.